Adds generation of songs with a length of over 30 seconds.
Adds the ability to continue songs.
Adds a seed option.
Disables (hopefully) the gradio analytics.
- Clone the repo:
git clone https://github.com/1aienthusiast/audiocraft-infinity-webui.git
- Install the requirements:
pip install -r requirements.txt
- Clone the Meta audiocraft repo inside the
repositories
folder:
cd repositories
git clone https://github.com/facebookresearch/audiocraft
cd ..
python webui.py
Run git pull
inside the root folder to update the webui, and the same command inside repositories/audiocraft
to update audiocraft.
Meta provides 4 pre-trained models. The pre trained models are:
small
: 300M model, text to music only - 🤗 Hubmedium
: 1.5B model, text to music only - 🤗 Hubmelody
: 1.5B model, text to music and text+melody to music - 🤗 Hublarge
: 3.3B model, text to music only - 🤗 Hub
Needs a GPU!
I recommend 12GB of VRAM for the large model.
For google colab you need to replace demo.launch()
with demo.queue().launch(share=True)
in webui.py
- The code in this repository is released under the AGPLv3 license as found in the LICENSE file.